A mobile phone app can detect COVID-19 infection in people’s voices, global respiratory experts will hear today.
Research carried out at the Institute of Data Science, Maastricht University, The Netherlands, say this artificial intelligence (AI) model is more accurate than lateral flow/rapid antigen tests and is cheap, quick and easy to use.
This means it can be used in low-income countries where PCR tests are expensive and/or difficult to distribute.
Wafaa Aljbawi, a researcher at the Institute, told delegates at the European Respiratory Society International Congress in Barcelona, Spain, that the AI model had 89% accuracy. Lateral flow accuracy depends on the brand and also vary considerably at detecting COVID infection in asymptomatic people.
“These promising results suggest that simple voice recordings and fine-tuned AI algorithms can potentially achieve high precision in determining which patients have COVID-19 infection,” she said.
“Such tests can be provided at no cost and are simple to interpret. Moreover, they enable remote, virtual testing and have a turnaround time of less than a minute. They could be used, for example, at the entry points for large gatherings, enabling rapid screening of the population.”
Because COVID-19 usually affects the upper respiratory track and vocal cords, Ms Aljbawi and her supervisors, Dr Sami Simons, pulmonologist at Maastricht University Medical Centre, and Dr Visara Urovi, also from the Institute of Data Science, examined if it was possible to use AI to analyse voices to detect COVID-19.
They used data from the University of Cambridge’s crowd-sourcing COVID-19 Sounds App that contains 893 audio samples from 4,352 healthy and non-healthy participants, 308 of whom had tested positive for COVID-19.
The app is installed on the user’s mobile phone, the participants report some basic information about demographics, medical history and smoking status, and then are asked to record some respiratory sounds. These include coughing three times, breathing deeply through their mouth three to five times, and reading a short sentence on the screen three times.
The researchers used Mel-spectrogram analysis, which identifies different voice features such as loudness, power and variation over time.
They found Long-Short Term Memory (LSTM), which is based on neural networks that mimic the way the human brain operates and recognises the underlying relationships in data, out-performed the other models.
It works with sequences, making it suitable for modelling signals collected over time, such as from the voice, because of its ability to store data in its memory.
Its overall accuracy was 89%, its ability to correctly detect positive cases (sensitivity) was 89%, and its ability to correctly identify negative cases (specificity) was 83%.
“These results show a significant improvement in the accuracy of diagnosing COVID-19 compared to state-of-the-art tests such as the lateral flow test,” said Ms Aljbawi.
“The lateral flow test has a sensitivity of only 56%, but a higher specificity rate of 99.5%. This is important as it signifies that the lateral flow test is misclassifying infected people as COVID-19 negative more often than our test.
“In other words, with the AI LSTM model, we could miss 11 out 100 cases who would go on to spread the infection, while the lateral flow test would miss 44 out of 100 cases.
“The high specificity of the lateral flow test means that only one in 100 people would be wrongly told they were COVID-19 positive when, in fact, they were not infected, while the LSTM test would wrongly diagnose 17 in 100 non-infected people as positive.
“However, since this test is virtually free, it is possible to invite people for PCR tests if the LSTM tests show they are positive.”
The researchers say their results now need to be validated with large numbers and since the project started, 53,449 audio samples from 36,116 participants have been collected and can be used to improve and validate the accuracy of the model.
In a second study presented at the Congress, Henry Glyde, a PhD student in the faculty of engineering at the University of Bristol, showed that AI could be harnessed via the myCOPD app to predict when patients with chronic obstructive pulmonary disease (COPD) might acute exacerbation.
The myCOPD app, established in 2016, is a cloud-based interactive app, developed by patients and clinicians and is available to use in the NHS. More than 15,000 COPD patients use it to help them manage their disease.
The researchers collected 45,636 records for 183 patients between August 2017 and December 2021. Of these, 45,007 were records of stable disease and 629 were exacerbations and the research team used these data to train AI models on 70% of the data and test it on 30%.
“The most recent AI model we developed has a sensitivity of 32% and a specificity of 95%. This means that the model is very good at telling patients when they are not about to experience an exacerbation, which may help them to avoid unnecessary treatment,” said Mr Glyde.
“It is less good at telling them when they are about to experience one. Improving this will be the focus of the next phase of our research.”
Abstract no: OA1626 Wafaa Aljbawi *Developing a multivariate prediction model for the detection of COVID-19 from crowd-sourced respiratory voice data* Presented in *Digital medicine for COVID-19* session.
Also available as a [pre-print paper]
Abstract no. PA2728 Henry Glyde *Exacerbation predictive modelling using real-world data from the myCOPD app*, Thematic poster *Digital health interventions in respiratory practice*.
Leave a Reply